Add prefetch builtins

Author: HendrikHuebner

clang/include/clang/CIR/Dialect/IR/CIROps.td

@@ -4116,7 +4116,7 @@ def CIR_PrefetchOp : CIR_Op<"prefetch"> {
     $locality is a temporal locality specifier ranging from (0) - no locality,
     to (3) - extremely local, keep in cache. If $locality is not present, the
     default value is 3.
-    
+
     $isWrite specifies whether the prefetch is for a 'read' or 'write'. If
     $isWrite is not specified, it means that prefetch is prepared for 'read'.
   }];
@@ -4150,7 +4150,7 @@ def CIR_ObjSizeOp : CIR_Op<"objsize", [Pure]> {
     When the `min` attribute is present, the operation returns the minimum
     guaranteed accessible size. When absent (max mode), it returns the maximum
     possible object size. Corresponds to `llvm.objectsize`'s `min` argument.
-    
+
     The `dynamic` attribute determines if the value should be evaluated at
     runtime. Corresponds to `llvm.objectsize`'s `dynamic` argument.
 

clang/lib/CIR/CodeGen/CIRGenBuiltinX86.cpp

@@ -20,6 +20,11 @@
 using namespace clang;
 using namespace clang::CIRGen;
 
+/// Get integer from a mlir::Value that is an int constant or a constant op.
+static int64_t getIntValueFromConstOp(mlir::Value val) {
+  return val.getDefiningOp<cir::ConstantOp>().getIntValue().getSExtValue();
+}
+
 template <typename... Operands>
 static mlir::Value emitIntrinsicCallOp(CIRGenFunction &cgf, const CallExpr *e,
                                        const std::string &str,
@@ -33,6 +38,28 @@ static mlir::Value emitIntrinsicCallOp(CIRGenFunction &cgf, const CallExpr *e,
       .getResult();
 }
 
+static mlir::Value emitPrefetch(CIRGenFunction &cgf, unsigned builtinID,
+                                const CallExpr *e,
+                                mlir::Value &addr, int64_t hint) {
+  CIRGenBuilderTy &builder = cgf.getBuilder();
+  mlir::Location location = cgf.getLoc(e->getExprLoc());
+  mlir::Type voidTy = builder.getVoidTy();
+  mlir::Value address = builder.createPtrBitcast(addr, voidTy);
+  bool isWrite{};
+  int locality{};
+
+  if (builtinID == X86::BI_mm_prefetch) {
+    isWrite = (hint >> 2) & 0x1;
+    locality = hint & 0x3;
+  } else {
+    isWrite = (builtinID == X86::BI_m_prefetchw);
+    locality = 0x3;
+  }
+
+  cir::PrefetchOp::create(builder, location, address, locality, isWrite);
+  return {};
+}
+
 mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID,
                                                const CallExpr *e) {
   if (builtinID == Builtin::BI__builtin_cpu_is) {
@@ -85,6 +112,9 @@ mlir::Value CIRGenFunction::emitX86BuiltinExpr(unsigned builtinID,
   case X86::BI_mm_sfence:
     return emitIntrinsicCallOp(*this, e, "x86.sse.sfence", voidTy);
   case X86::BI_mm_prefetch:
+  case X86::BI_m_prefetch:
+  case X86::BI_m_prefetchw:
+      return emitPrefetch(*this, builtinID, e, ops[0], getIntValueFromConstOp(ops[1]));
   case X86::BI__rdtsc:
   case X86::BI__builtin_ia32_rdtscp:
   case X86::BI__builtin_ia32_lzcnt_u16:

clang/test/CIR/CodeGen/X86/prefetchw-builtin.c

@@ -0,0 +1,36 @@
+
+// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +sse -fclangir -emit-cir -o %t.cir -Wall -Werror
+// RUN: FileCheck --check-prefix=CIR --input-file=%t.cir %s
+// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +sse -fclangir -emit-llvm -o %t.ll -Wall -Werror
+// RUN: FileCheck --check-prefixes=LLVM --input-file=%t.ll %s
+
+// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +sse -fno-signed-char -fclangir -emit-cir -o %t.cir -Wall -Werror
+// RUN: FileCheck --check-prefix=CIR --input-file=%t.cir %s
+// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +sse -fclangir -emit-llvm -o %t.ll -Wall -Werror
+// RUN: FileCheck --check-prefixes=LLVM --input-file=%t.ll %s
+
+// RUN: %clang_cc1 -x c -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +sse -emit-llvm -o - -Wall -Werror | FileCheck %s -check-prefix=OGCG
+// RUN: %clang_cc1 -x c++ -flax-vector-conversions=none -ffreestanding %s -triple=x86_64-unknown-linux -target-feature +sse -emit-llvm -o - -Wall -Werror | FileCheck %s -check-prefix=OGCG
+
+
+#include <x86intrin.h>
+
+void test_m_prefetch(void *p) {
+  // CIR-LABEL: test_m_prefetch
+  // LLVM-LABEL: test_m_prefetch
+  // OGCG-LABEL: test_m_prefetch
+  return _m_prefetch(p);
+  // CIR: cir.prefetch read locality(0) %{{.*}} : !cir.ptr<!void>
+  // LLVM: call void @llvm.prefetch.p0(ptr {{.*}}, i32 0, i32 0, i32 1)
+  // OGCG: call void @llvm.prefetch.p0(ptr {{.*}}, i32 0, i32 0, i32 1)
+}
+
+void test_m_prefetch_w(void *p) {
+  // CIR-LABEL: test_m_prefetch_w
+  // LLVM-LABEL: test_m_prefetch_w
+  // OGCG-LABEL: test_m_prefetch_w
+  return _m_prefetchw(p);
+  // CIR: cir.prefetch write locality(0) %{{.*}} : !cir.ptr<!void>
+  // LLVM: call void @llvm.prefetch.p0(ptr {{.*}}, i32 0, i32 0, i32 1)
+  // OGCG: call void @llvm.prefetch.p0(ptr {{.*}}, i32 0, i32 0, i32 1)
+}

clang/test/CIR/CodeGen/X86/sse-builtins.c

@@ -26,3 +26,21 @@ void test_mm_sfence(void) {
   // LLVM: call void @llvm.x86.sse.sfence()
   // OGCG: call void @llvm.x86.sse.sfence()
 }
+
+void test_mm_prefetch(char const* p) {
+  // CIR-LABEL: test_mm_prefetch
+  // LLVM-LABEL: test_mm_prefetch
+  _mm_prefetch(p, 0);
+  // CIR: cir.prefetch read locality(0) %{{.*}} : !cir.ptr<!void>
+  // LLVM: call void @llvm.prefetch.p0(ptr {{.*}}, i32 0, i32 0, i32 1)
+  // OGCG: call void @llvm.prefetch.p0(ptr {{.*}}, i32 0, i32 0, i32 1)
+}
+
+void test_mm_prefetch_local(char const* p) {
+  // CIR-LABEL: test_mm_prefetch_local
+  // LLVM-LABEL: test_mm_prefetch_local
+  _mm_prefetch(p, 3);
+  // CIR: cir.prefetch read locality(3) %{{.*}} : !cir.ptr<!void>
+  // LLVM: call void @llvm.prefetch.p0(ptr {{.*}}, i32 0, i32 3, i32 1)
+  // OGCG: call void @llvm.prefetch.p0(ptr {{.*}}, i32 0, i32 3, i32 1)
+}